Global manhunt will leverage social media to find suspects | Geek Gestalt – CNET News

Global manhunt will leverage social media to find suspects | Geek Gestalt – CNET News.

If you had to track down fugitives hidden in five cities around the world, would one day and a $5,000 reward be enough to succeed? And if so, how?

That’s what the people behind the TAG Challenge want to know–and what the whole world will soon find out.

On March 31, mug shots of five “suspects” will be published, and it’ll be game on in a global hunt for “jewel thieves” in Bratislava, Slovakia; Stockholm; London; Washington, D.C.; and New York City, each of whom will spend 12 hours that day in public areas. The first team to upload photographs of each of the five by noon eastern time on April 1 will win the competition–and with it, a ton of international glory.

Then again, there’s a good chance no one will win, given the limited time available to contestants.

The competition is based in part on 2009’s DARPA Red Balloon Challenge–in which DARPA hid 10 balloons around the United States and offered a $40,000 prize to the first team that could find them all in a single day.

GUEST SPEAKER: Nicholas Diakopoulos

Title: Computational Journalism: Social Media Visual Analytics for Journalistic Inquiry

Nicholas Diakopoulos (GA Tech, PhD, 2009).
Rutgers University
Date/Day: Thursday 4/15/2010
Time: 1:30p
Location: CCB 102

What is the impact that computing can and will have on the changing
landscape of news production and consumption? In this talk I will
introduce Computational Journalism as the application of computing to
the processes of journalism including information gathering,
organization and sensemaking, communication and presentation, and
dissemination and public interaction with news information, all while
upholding values of journalism such as balance, accuracy, and
objectivity. I will then present recent work related to visual and
analytic tools for helping to enhance journalists’ and consumers’
abilities to make sense of public commentary on televised news events
such as debates and speeches. This work suggests opportunities for
computing to enhance both the ability of journalists to leverage
public response to news events, as well as for the public to have more
meaningful experiences when participating in online news commentary

Nicholas Diakopoulos is a Computing Innovation Fellow at the School of
Communication and Information at Rutgers University. He received his
Ph.D. in Computer Science from the School of Interactive Computing at
the Georgia Institute of Technology in 2009. His research interests
span human computer interaction, information visualization, and
multimedia content analysis with themes from media including
journalism, collaborative authorship and annotation, and games.

GUEST SPEAKER: Dan Huttenlocher (Cornell) Tue 4/13/2010 at 1:30 in Klaus 1116 West on “Mapping the World’s Photos”

Mapping the World’s Photos

Daniel Huttenlocher
Cornell University

Date: Tuesday 4/13/2010
Time: 1:30p – 3:00p.
Location: Klaus 1116 West

We investigate how to organize a large collection of geotagged photos, working with a dataset of about 35 million images collected from Flickr. Our approach combines content analysis based on text tags and image data with structural analysis based on geospatial data. We use the spatial distribution of where people take photos to define a relational structure between the photos that are taken at popular places. We then study the interplay between this structure and the content, using classification methods for predicting such locations from visual, textual and temporal features of the photos. We find that combined visual and temporal features improve the ability to estimate the location of a photo, compared to using just textual or visual features alone. We illustrate using these techniques to structure a large collection of geotagged photos, while also revealing various interesting properties about popular cities and landmarks at a global scale.